User | EdwinValdezEXD |
Upload Date | November 20 2024 09:43 AM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | CPU |
Device | Apple M2 |
System Information | |
---|---|
Operating System | macOS 15.1.1 (Build 24B91) |
Model | MacBook Pro (13-inch, 2022) |
Model ID | Mac14,7 |
Motherboard | Mac14,7 |
CPU Information | |
---|---|
Name | Apple M2 |
Topology | 1 Processor, 8 Cores |
Identifier | Apple M2 |
Base Frequency | 3.46 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 8.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1370
254.8 IPS |
|
Image Classification (HP)
|
100% |
2503
465.5 IPS |
|
Image Classification (Q)
|
96% |
1752
327.1 IPS |
|
Image Segmentation (SP)
|
100% |
1523
24.7 IPS |
|
Image Segmentation (HP)
|
100% |
2461
39.9 IPS |
|
Image Segmentation (Q)
|
99% |
2821
45.7 IPS |
|
Pose Estimation (SP)
|
100% |
6848
7.99 IPS |
|
Pose Estimation (HP)
|
100% |
14896
17.4 IPS |
|
Pose Estimation (Q)
|
95% |
12853
15.1 IPS |
|
Object Detection (SP)
|
100% |
1542
122.3 IPS |
|
Object Detection (HP)
|
97% |
2844
226.4 IPS |
|
Object Detection (Q)
|
94% |
2051
163.5 IPS |
|
Face Detection (SP)
|
100% |
3098
36.8 IPS |
|
Face Detection (HP)
|
100% |
6016
71.5 IPS |
|
Face Detection (Q)
|
100% |
3487
41.4 IPS |
|
Depth Estimation (SP)
|
100% |
5643
43.5 IPS |
|
Depth Estimation (HP)
|
98% |
11600
89.7 IPS |
|
Depth Estimation (Q)
|
85% |
8032
62.8 IPS |
|
Style Transfer (SP)
|
100% |
18677
24.0 IPS |
|
Style Transfer (HP)
|
100% |
28488
36.6 IPS |
|
Style Transfer (Q)
|
96% |
23707
30.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
4086
150.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
4831
178.4 IPS |
|
Image Super-Resolution (Q)
|
99% |
3562
131.5 IPS |
|
Text Classification (SP)
|
100% |
2215
2.96 KIPS |
|
Text Classification (HP)
|
100% |
3702
4.94 KIPS |
|
Text Classification (Q)
|
93% |
3703
4.97 KIPS |
|
Machine Translation (SP)
|
100% |
3515
60.5 IPS |
|
Machine Translation (HP)
|
98% |
5777
99.8 IPS |
|
Machine Translation (Q)
|
98% |
5798
100.2 IPS |